👋 Hi there! Xin Wu (吴欣)

I am currently pursuing my Ph.D. degree in Computer Science and Technology at Southwest Jiaotong University (SWJTU), where I am fortunate to be advised by Prof. Fei Teng.

XIN WU (Xtreme-scale, Interpretable, Novelty-resilient, Wide-domain, and Uncertainty-aware AI) represents my core research vision for building trustworthy, adaptive, and generalizable AI systems in dynamic cluster environments. Situated at the intersection of Service Computing, AI Infrastructure, and AIOps, my research interests include, but are not limited to:

• Workload Prediction & Resource Management: Developing data-driven and uncertainty-aware methodologies for dynamic resource provisioning and workload forecasting in dynamic computing infrastructures.

• Anomaly Detection & Performance Diagnosis: Building robust and interpretable models to detect system anomalies, isolate failure modes, and diagnose performance bottlenecks under non-stationary cluster workloads.

• Trustworthy AI for Systems: Advancing interpretable learning, out-of-distribution (OOD) robustness, and domain generalization to ensure the safety and reliability of autonomous cluster management.

🤔 Only two things make me move.

i. ⌨️ 🧱 Working with Attention. It’s all I need.

ii. Life was like a box of chocolates 🍫. You never know what you’re going to get.

If you are interested in any aspect of me, I would love to chat and collaborate, please contact xinwu5386[at]gmail.com or wu1351658806[at]163.com.

🔥 News

📝 Selected Papers

KDD 2026

Taming Multi-Dimensional Tail: A Factorized Tail-Interaction Framework for Hyperscale Cloud Workload Forecasting

Xin Wu, Fei Teng (*), Chen Yang, Tianrui Li

Proceedings of the 32nd SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD‘26), 2026.

Code

DAC 2026

PRISM: Dynamic Primitive-Based Forecasting for Large-Scale GPU Cluster Workloads

Xin Wu, Fei Teng (*), Xingwang Li, Bin Zheng, Qiang Duan

Proceedings of the 63rd ACM/IEEE Design Automation Conference (DAC‘26), 2026.

Code

TMM 2026

Exploring Partial Multi-Label Learning via Integrating Semantic Co-occurrence Knowledge

Xin Wu, Fei Teng (*), Yue Feng, Kaibo Shi, Zhuosheng Lin, Ji Zhang, James Wang.

IEEE Transactions on Multimedia (TMM), 2026.

Project | Code

Inf. Fusion 2026

ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification

Xin Wu, Fei Teng (*), Ji Zhang, Xingwang Li, Yuxuan Liang.

Information Fusion, 2026.

Project | Code

Inf. Fusion 2026

Out-of-Distribution Generalization in Time Series: A Survey

Xin Wu, Fei Teng (*), Xingwang Li, Ji Zhang, Tianrui Li, Qiang Duan.

Information Fusion, 2026.

Project | Code

KBS 2023

CTransCNN: Combining Transformer and CNN in Multilabel Medical Image Classification

Xin Wu, Yue Feng (*), Hong Xu, Zhuosheng Lin, Tao Chen, Shengke Li, Shihan Qiu, Qichao Liu, Yuangang Ma, Shuangsheng Zhang.

Knowledge-Based Systems (KBS), 2023.

Project | Code | BibTeX

Front. Comput. Sci.

Review of Deep Learning in Classification of Tongue Image

Xin Wu, Hong Xu, Zhuosheng Lin, Shengke Li, Huilin Liu, Yue Feng (*).

Journal of Frontiers of Computer Science & Technology, 2023.

BibTeX

PRCV 2023

CheXNet: Combing Transformer and CNN for Thorax Disease Diagnosis from Chest X-ray Images

Xin Wu, Yue Feng (*), Hong Xu, Zhuosheng Lin, Shengke Li, Shihan Qiu, QiChao Liu, Yuangang Ma.

Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023.

Code | BibTeX

Links

• Jennifier’s paper writing tips. I try to follow this guideline in my paper writing.

• Andrew N’s paper reading tips. I follow this guideline when reading papers.